Submission

Put the ipynb file and html file in the github branch you created in the last assignment and submit the link to the commit in brightspace

from plotly.offline import init_notebook_mode
import plotly.io as pio
import plotly.express as px


init_notebook_mode(connected=True)
pio.renderers.default = "plotly_mimetype+notebook"

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

Question 1:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

# YOUR CODE HERE
# Filter data for the year 2007
df_2007 = df[df['year'] == 2007]

# Sort the data by continent and population
df_2007_sorted = df_2007.sort_values(by=['continent', 'pop']).groupby('continent').sum().reset_index()


# Create the barplot
fig = px.bar(
    df_2007_sorted,
    x = 'pop',
    y = 'continent',
    color= 'continent',  # Different colors for each continent
    title= 'Population of Continents in 2007'
)

# Customize layout of the figure
fig.update_layout(
    showlegend=False,  # Hide legend
)

# Show the plot
fig.show()

Question 2:

Sort the order of the continent for the visualisation

Hint: Use axis layout setting

# YOUR CODE HERE
# Filter data for the year 2007
df_2007 = df[df['year'] == 2007]

# Sort the data by continent and population
df_2007_sorted = df_2007.sort_values(by=['continent', 'pop']).groupby('continent').sum().reset_index()


# Create the barplot
fig = px.bar(
    df_2007_sorted,
    x = 'pop',
    y = 'continent',
    color= 'continent',  # Different colors for each continent
    title= 'Population of Continents in 2007'
)

# Customize layout of the figure
fig.update_layout(
    showlegend=False,  # Hide legend,
    yaxis={'categoryorder': 'total ascending'}   # Sort the order of the continent for the visualisation
)


# Show the plot
fig.show()

Question 3:

Add text to each bar that represents the population

# YOUR CODE HERE
# Filter data for the year 2007
df_2007 = df[df['year'] == 2007]

# Sort the data by continent and population
df_2007_sorted = df_2007.sort_values(by=['continent', 'pop']).groupby('continent').sum().reset_index()


# Create the barplot
fig = px.bar(
    df_2007_sorted,
    x = 'pop',
    y = 'continent',
    color= 'continent',  # Different colors for each continent
    text_auto='.2s',
    title= 'Population of Continents in 2007'
)

# Customize layout of the figure
fig.update_layout(
    showlegend=False,  # Hide legend,
    yaxis={'categoryorder': 'total ascending'},   # Sort the order of the continent for the visualisation
)


# Show the plot
fig.show()

Question 4:

Thus far we looked at data from one year (2007). Lets create an animation to see the population growth of the continents through the years

# YOUR CODE HERE

# Sort the data by continent and population
df_sorted = df.sort_values(by=['continent', 'pop'])


# Create the barplot
animated_fig = px.histogram(
    df_sorted,
    x = 'pop',
    y = 'continent',
    color= 'continent',  # Different colors for each continent
    title= 'Population of Continents over time'
)

# Create animation
animated_fig = px.histogram(df, x="pop", y="continent", color="continent",
        animation_frame="year", range_x=[0,4000000000])

# Customize layout of the figure
animated_fig.update_layout(
    showlegend=False,  # Hide legend,
    yaxis={'categoryorder': 'total ascending'},   # Sort the order of the continent for the visualisation
)

# Show figure
animated_fig.show()

Question 5:

Instead of the continents, lets look at individual countries. Create an animation that shows the population growth of the countries through the years

# YOUR CODE HERE
# Create animation
animated_fig = px.histogram(df, x="pop", y="country", color="country",
        animation_frame="year", range_x=[0,1400000000])

# Customize layout of the figure
animated_fig.update_layout(
        showlegend=False,  # Hide legend,
        yaxis={'categoryorder': 'total ascending'},   # Sort the order of the continent for the visualisation
        title= 'Population of Countries over time'
)

# Show figure
animated_fig.show()

Question 6:

Clean up the country animation. Set the height size of the figure to 1000 to have a better view of the animation

# YOUR CODE HERE
# Create animation
animated_fig = px.histogram(df, x="pop", y="country", color="country",
        animation_frame="year", range_x=[0,1400000000])

# Customize layout of the figure
animated_fig.update_layout(
    showlegend=False,  # Hide legend,
    yaxis={'categoryorder': 'total ascending'},   # Sort the order of the continent for the visualisation
    height=1000,
    title= 'Population of Countries over time'
)

# Show figure
animated_fig.show()

Question 7:

Show only the top 10 countries in the animation

Hint: Use the axis limit to set this.

# YOUR CODE HERE

# # Sort the data by continent and population
# df_sorted = df.sort_values(by=['country', 'pop'])


# # Create the barplot
# animated_fig = px.histogram(
#     df_sorted,
#     x = 'pop',
#     y = 'country',
#     color= 'country',  # Different colors for each continent
#     title= 'Population of Top 10 Countries over time'
# )

# Create animation
animated_fig = px.histogram(df,
                            x="pop", 
                            y="country", 
                            color="country",
                            animation_frame="year", 
                            range_x=[0,1400000000],
                            range_y=[131.5,142]
                            
)

# Customize layout of the figure
animated_fig.update_layout(
    showlegend=False,        
    yaxis={'categoryorder': 'total ascending'},
    height=1000,
    title='Population of Top 10 Countries over time'
)

# Show figure
animated_fig.show()